arXiv cs.AI· Yuzhi Yang, Brahim Mefgouda, Hang Zou, Lina Bariah, Anis Bara, Yuhuan Lu, Hao Zhang, Merouane Debbah·· 13 小时前AI 评分18
JEPA 启发的潜在场预测用于稀疏导频 MIMO-OFDM 信道重建
JEPA-Inspired Latent Field Prediction for Sparse-Pilot MIMO-OFDM Channel Reconstruction
AI 导读
研究者提出一种受 JEPA 启发的场世界模型，将 CSI 观测映射为潜在时频 token，从历史多频段上下文预测被掩码或未来的潜在场状态，再与稀疏含噪导频融合以重建完整 MIMO-OFDM 信道。射线追踪实验显示，该方法在 NMSE 上优于仅用导频和直接重建的基线，表明潜在场预测可作为稀疏导频信道获取的有效先验。
正文 · 原文
Abstract:Accurate acquisition of full channel state information (CSI) is essential for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) wireless systems, while dense pilot-based estimation incurs substantial overhead. Directly minimizing the prediction error over raw CSI coefficients is fragile in realistic propagation environments, since small-scale fading, mobility, local scattering, and small spatial perturbations can induce large phase-sensitive variations. Nevertheless, wireless channels contain strong spatial, temporal, and frequency-domain correlations that can be more predictably represented in a latent propagation-field domain. Motivated by this observation, we propose a joint-embedding predictive architecture (JEPA)-inspired field world model, defined as a latent predictive model of the wireless propagation field, for sparse-pilot channel reconstruction. The model maps CSI observations into latent time-frequency tokens, predicts masked or future latent field states from historical multi-band context, and fuses the predicted latent prior with sparse noisy current pilots to reconstruct the full MIMO-OFDM channel. Ray-tracing experiments show that the proposed method improves normalized mean square error (NMSE) over pilot-only and direct reconstruction baselines, supporting latent field prediction as an effective prior for sparse-pilot channel acquisition.
| Subjects: | Signal Processing (eess.SP); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37391 [eess.SP] |
| (or arXiv:2610.37391v1 [eess.SP] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37391 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Brahim Mefgouda [view email]
[v1]
Tue, 27 Oct 2026 15:14:41 UTC (10,059 KB)
来源：arXiv cs.AI · arxiv.org